nanobanana-mcp

nanobanana-mcp

MCP server for AI image generation supporting text-to-image and image-to-image editing via any OpenAI-compatible service, with configurable models, aspect ratios, and sizes.

Category
Visit Server

README

NanoBanana

AI 图像生成工具,使用 OpenAI 兼容协议,支持任何兼容的图像生成服务。

特性

  • 🎨 文生图 - 根据文本描述生成图片
  • 🖼️ 图生图 - 基于参考图片生成新图片
  • 🔄 多 Provider 兼容 - OpenRouter 等
  • 📦 双版本支持 - MCP Server + Clawdbot Plugin

版本选择

版本 适用场景 目录
MCP Server Claude Desktop / Claude Code src/
Clawdbot Plugin Clawdbot AI 助手 clawdbot-plugin/

MCP Server

用于 Claude Desktop 和 Claude Code。

快速使用

npx nanobanana-mcp

从源码安装

git clone https://github.com/superboolgithub/nanobanana-mcp.git
cd nanobanana-mcp
npm install
npm run build

环境变量

变量名 必填 说明 默认值
NANOBANANA_API_KEY API 密钥 -
NANOBANANA_BASE_URL API 基础 URL -
NANOBANANA_OUTPUT_DIR 图片输出目录 -
NANOBANANA_DEFAULT_ASPECT_RATIO 默认宽高比 1:1
NANOBANANA_DEFAULT_IMAGE_SIZE 默认图片尺寸 1K
NANOBANANA_DEFAULT_MODEL 默认模型 google/gemini-2.5-flash-image-preview

Claude Desktop 配置

claude_desktop_config.json 中添加:

{
  "mcpServers": {
    "nanobanana": {
      "command": "npx",
      "args": ["-y", "nanobanana-mcp"],
      "env": {
        "NANOBANANA_API_KEY": "your-api-key",
        "NANOBANANA_BASE_URL": "https://openrouter.ai/api",
        "NANOBANANA_OUTPUT_DIR": "/path/to/output"
      }
    }
  }
}

Claude Code 配置

~/.claude.json 中添加:

{
  "mcpServers": {
    "nanobanana": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "nanobanana-mcp"],
      "env": {
        "NANOBANANA_API_KEY": "your-api-key",
        "NANOBANANA_BASE_URL": "https://openrouter.ai/api",
        "NANOBANANA_OUTPUT_DIR": "/path/to/output"
      }
    }
  }
}

Clawdbot Plugin

用于 Clawdbot AI 助手。

安装

cp -r clawdbot-plugin ~/.clawdbot/extensions/nanobanana

配置

~/.clawdbot/clawdbot.json 中添加:

{
  "plugins": {
    "entries": {
      "nanobanana": {
        "enabled": true,
        "config": {
          "apiKey": "your-api-key",
          "baseUrl": "https://openrouter.ai/api",
          "outputDir": "/tmp/nanobanana",
          "defaultAspectRatio": "1:1",
          "defaultImageSize": "1K",
          "defaultModel": "google/gemini-2.5-flash-image-preview"
        }
      }
    }
  }
}

配置项

配置项 必填 说明 默认值
apiKey API 密钥 -
baseUrl API 基础 URL -
outputDir 图片输出目录 /tmp/nanobanana
defaultAspectRatio 默认宽高比 1:1
defaultImageSize 默认图片尺寸 1K
defaultModel 默认模型 google/gemini-2.5-flash-image-preview

工具说明

generate_image - 文生图

根据文本描述生成图片。

参数:

  • prompt (必填) - 图片描述,最大 5000 字符
  • aspectRatio - 宽高比
  • imageSize - 图片尺寸
  • model - 模型名称

edit_image - 图生图

基于参考图片生成新图片。

参数:

  • prompt (必填) - 图片描述
  • referenceImageUrl (必填) - 参考图片 URL
  • aspectRatio - 宽高比
  • imageSize - 图片尺寸
  • model - 模型名称

参数选项

宽高比 (aspectRatio)

分辨率 说明
1:1 1024×1024 方形(默认)
16:9 1344×768 横版宽屏
9:16 768×1344 竖版
4:3 1184×864 横版
3:4 864×1184 竖版
2:3 832×1248 竖版
3:2 1248×832 横版
4:5 896×1152 竖版
5:4 1152×896 横版
21:9 1536×672 超宽屏

图片尺寸 (imageSize)

说明
1K 标准分辨率(默认)
2K 高分辨率
4K 最高分辨率

兼容模型

  • google/gemini-2.5-flash-image-preview - 快速生成
  • google/gemini-3-pro-image-preview - 高质量
  • gemini-2.5-flash-image - Gemini Flash
  • black-forest-labs/flux.2-pro - Flux Pro
  • 其他支持图像生成的模型

API 协议

使用 OpenAI Chat Completions API 格式:

请求

POST /v1/chat/completions
Content-Type: application/json
Authorization: Bearer <api-key>

{
  "model": "gemini-2.5-flash-image",
  "messages": [
    { "role": "user", "content": "Generate a beautiful sunset" }
  ],
  "modalities": ["image", "text"],
  "image_config": {
    "aspect_ratio": "16:9",
    "image_size": "2K"
  }
}

响应格式

支持两种响应格式:

格式 1:OpenRouter 风格

{
  "choices": [{
    "message": {
      "content": "Here's your image",
      "images": [{
        "image_url": { "url": "data:image/png;base64,..." }
      }]
    }
  }]
}

格式 2:Markdown 内嵌

{
  "choices": [{
    "message": {
      "content": "![image](data:image/png;base64,...)"
    }
  }]
}

兼容的 Provider

任何使用 OpenAI Chat Completions API 格式的图像生成服务:


使用示例

"生成一张可爱的猫咪图片"
"生成一张 4K 横版的日落海滩风景"
"基于这张图片,生成一个卡通风格的版本"

开发

# 安装依赖
npm install

# 开发模式
npm run dev

# 构建
npm run build

# 运行
npm start

License

MIT

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured